Optimized the Variation of Attribute for Stock Market Prediction Using Machine Learning
DOI:
https://doi.org/10.17762/msea.v71i4.521Abstract
The wealth of currency and nation depends on the growth of the stock market. The prediction of stock price varies according to their parameters such as open price, close price and strike price. The variation of parameters creates an unstable and volatile situation for the stock market. The unstable nature of stock market diverts customers for the investments. In this paper proposed cascaded machine learning algorithm for the stock price prediction. The cascaded machine learning algorithm work with an optimized variance of stock parameters. The process of parameters optimization achieves by particle swarm optimization. The particle swarm optimization is a memory-based and iterative process. The proposed algorithm implemented in MATLAB software and tested with NSE data of different banks such as HDFC, IDBI and AXIS bank.